VisualLens: Personalization through Task-Agnostic Visual History
benchmarksgoogle-review-vhistory lengthshit@3multimodal large language modelsmultimodal recommendationpersonalizationrecommendation systemsrobustnesstask-agnostic insightsunseen content categoriesuser profile extractionvisual historyvisuallensyelp-v
Existing recommendation systems either rely on user interaction logs, such as online shopping history for shopping recommendations, or focus on text signals. However, item-based histories are not always accessible and generalizable for multimodal recommendation. We hypothesize that a user's visual history